CN103587528A - Lane change process crossing moment prediction device and method - Google Patents
Lane change process crossing moment prediction device and method Download PDFInfo
- Publication number
- CN103587528A CN103587528A CN201310475750.XA CN201310475750A CN103587528A CN 103587528 A CN103587528 A CN 103587528A CN 201310475750 A CN201310475750 A CN 201310475750A CN 103587528 A CN103587528 A CN 103587528A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- processing unit
- data processing
- constantly
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 81
- 238000012545 processing Methods 0.000 claims abstract description 57
- 230000005540 biological transmission Effects 0.000 claims abstract description 4
- 238000005070 sampling Methods 0.000 claims description 8
- 238000013480 data collection Methods 0.000 claims description 4
- 238000006467 substitution reaction Methods 0.000 claims description 4
- 238000005259 measurement Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 abstract 2
- 238000009434 installation Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000002045 lasting effect Effects 0.000 description 2
- 230000033001 locomotion Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/10—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/18—Propelling the vehicle
- B60W30/18009—Propelling the vehicle related to particular drive situations
- B60W30/18163—Lane change; Overtaking manoeuvres
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2520/00—Input parameters relating to overall vehicle dynamics
- B60W2520/10—Longitudinal speed
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2555/00—Input parameters relating to exterior conditions, not covered by groups B60W2552/00, B60W2554/00
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Traffic Control Systems (AREA)
- Image Processing (AREA)
Abstract
The invention belongs to the technical field of lane change process crossing moment prediction and discloses a lane change process crossing moment prediction device and method. The device comprises a vehicular CAN bus, a data processing unit, a visual sensor mounted above the center of a front windscreen of a vehicle, and a speed sensor mounted on a vehicle transmission. The speed sensor is electrically connected with the vehicular CAN bus. The data processing unit is electrically connected with both the vehicular CAN bus and the visual sensor.
Description
Technical field
The invention belongs to the process of changing and get over line electric powder prediction constantly, particularly a kind of process of changing is got over line prediction unit and Forecasting Methodology thereof constantly.
Background technology
At present ，Huan road forewarn system adopts advanced sensors to monitor ，Dang Huan road process to traffic environment chaufeur to be carried out to early warning when dangerous conventionally.Change forewarn system and pay close attention to the relative motion relation of other vehicles of target vehicle rear, Zi Cheyuhuan road in the process of changing, while only having Dang Huan road vehicle to cross lane mark from this track to enter into object track, just likely with the vehicle generation traffic conflict at rear, target track.As can be seen here, the prediction process of changing is got over the line problem that Shi Huan road forewarn system emphasis need to solve constantly accurately.
Change track and be vehicle when carrying out lane change, the path of process on road plane.Change to get over when line is vehicle Huan road constantly and reach all moment of crossing lane mark, therefore, want to determine to change and get over line constantly, need first obtain changing track.At present, trace of lane-changing is used as to circular arc to some researchists or sine curve is processed, or utilize the multinomial locus model with continuous curvature to replace arc track model to calculate in vehicle lane-changing process in longitudinal direction and position in a lateral direction etc.Part Study personnel constantly distribute and discuss the actual more line that changes process, but do not relate to more line moment Forecasting Methodology.In general, also lack at present actv. truly the process of changing get over constantly Forecasting Methodology of line.
Summary of the invention
The object of the invention is to propose a kind of more line prediction unit and Forecasting Methodology ，Gai Huan road process thereof line prediction unit small investment constantly more constantly of process of changing, be applicable to large-scale promotion.Gai Huan road process get over line constantly Forecasting Methodology there is intellectuality, automation, without operation, feature that reliability is high.
For realizing above-mentioned technical purpose, the present invention adopts following technical scheme to be achieved.
Technical scheme one:
Process is got over a constantly prediction unit of line, comprising: vehicle-mounted CAN bus, data processing unit, be arranged on the vision sensor of vehicle front windshield centre top and be arranged on the car speed sensor on transmission for vehicles;
Described car speed sensor is electrically connected to vehicle-mounted CAN bus, and described data processing unit is electrically connected to respectively vehicle-mounted CAN bus and vision sensor.
The feature of the technical program and further improvement are:
Described vision sensor is towards vehicle front road surface, and described vision sensor is the vision sensor in auto against forewarn system (AWS), and the survey precision of described vision sensor is 5cm, and measurement range is ± 635cm that output frequency is 10Hz.
Described data processing unit is encapsulated in can, and is arranged on vehicle cab operation bench below; Described data processing unit is electrically connected to respectively vehicle-mounted CAN bus and vision sensor by I/O interface, and the data sampling frequency of described data processing unit is 10Hz.
Described car speed sensor is magneto-electric car speed sensor, and the sampling precision of described car speed sensor is 0.01km/h.
The mouth of described data processing unit is electrically connected with read-out, and described read-out is arranged on meter panel of motor vehicle.
Technical scheme two:
Process is got over a line Forecasting Methodology constantly, based on above-mentioned a kind of process of changing, gets over line prediction unit constantly, comprises the following steps:
Raw data acquisition: make vehicle in advance repeatedly left/right-hand lane change, changing in process at every turn, data processing unit acquisition time parameter, the transverse distance that vision sensor detects vehicle and left/right lane mark is sent to data processing unit; Meanwhile, car speed sensor is sent to data processing unit by the real-time speed of a motor vehicle by vehicle-mounted CAN bus;
Set up vehicle lane-changing matching relational database: for vehicle left/right-hand lane changes, first, the difference of the speed of a motor vehicle, divides into groups the original data of data processing unit collection when changing, and obtains vehicle and changes matching relational database to left/right; Original data comprises: the vehicle obtaining in raw data acquisition and the transverse distance of left/right lane mark and corresponding acquisition time, and described vehicle changes matching relational database to left/right and comprises and respectively organize original data;
Measured data gathers: when carry out left/right-hand lane of vehicle is changed, data processing unit acquisition time parameter, vision sensor detects the transverse distance of vehicle and left/right lane mark, and the transverse distance of vehicle and left/right lane mark is sent to data processing unit; Meanwhile, car speed sensor is sent to data processing unit by the real-time speed of a motor vehicle by vehicle-mounted CAN bus;
Obtain more line required cross travel matching relational expression constantly of prediction: in the setting-up time section after vehicle starts to change, the measured data of data processing unit collection is carried out to the matching of M order polynomial, draw M order polynomial f
1and f
1matched curve, M is greater than 3 natural number, the starting point Wei Huan road zero hour of described setting-up time section, described measured data is included in the vehicle that obtains in measured data collection and the transverse distance of left/right lane mark and the corresponding acquisition time with it; At vehicle, to left/right, change in matching relational database, every group of original data is divided into and is positioned at the leading portion original data of corresponding setting-up time section and is positioned at the back segment original data after corresponding setting-up time section, respectively each group leading portion original data is carried out to the matching of M order polynomial, obtain several M order polynomials and several corresponding matched curves; In described several matched curves, obtain and f
1the immediate matched curve L of matched curve
w, and with matched curve L
wcorresponding M order polynomial f
w; At vehicle, to left/right, change in matching relational database, obtain and described M order polynomial f
wcorresponding leading portion original data D
wf, and with leading portion original data D
wfcorresponding back segment original data D
wb; By back segment original data D
wbthe measured data gathering in setting-up time section with data processing unit combines, form predicted data, then described predicted data is carried out to the matching of M order polynomial, obtain more line moment projected relationship formula y=f (t), y represents the transverse distance of vehicle and left/right lane mark, and t represents to change and gets over line constantly;
Determine to change and get over line constantly: the arbitrary moment after setting-up time section, the transverse distance of the vehicle that data processing unit is obtained and left/right lane mark, substitution is got in line moment projected relationship formula y=f (t), draws to change to get over line constantly.
The feature of the technical program and further improvement are:
In setting up the process of vehicle lane-changing matching relational database, after obtaining respectively organizing original data, every group of original data carried out to the matching of M order polynomial, thereby obtain vehicle and change matching relational database to left/right, described vehicle changes matching relational database to left/right and comprises that vehicle corresponding under different speed of a motor vehicle conditions changes vehicle corresponding under cross travel matched curve, different speed of a motor vehicle condition to left/right and changes cross travel polynomial fitting and respectively organize original data to left/right.
Read-out is electrically connected to the mouth of data processing unit, after carrying out data processing, the more line in vehicle Huan road process is sent to read-out constantly.
Beneficial effect of the present invention is: Gai Huan road process is got over line prediction unit small investment constantly, is applicable to large-scale promotion.Gai Huan road process get over line constantly Forecasting Methodology there is intellectuality, automation, without operation, feature that reliability is high.
Accompanying drawing explanation
Fig. 1 is the position view of vision sensor of the present invention and data processing unit;
Fig. 2 is that a kind of process of changing of the present invention is got over the line circuit connection diagram of prediction unit constantly.
The specific embodiment
Below in conjunction with accompanying drawing, the invention will be further described:
For the more line time to vehicle Huan road process is predicted accurately, in embodiments of the present invention, first need to carry out the installation of related device, the detailed process that device is installed is as follows:
With reference to Fig. 1, it is the position view of vision sensor of the present invention and data processing unit.The vision sensor that vision sensor 1 adopts in auto against forewarn system (AWS), its survey precision is 5cm, measurement range is ± 635cm.Vision sensor 1 is arranged on the Centromedian top of shield glass, and level is installed, and camera lens is towards the road surface of vehicle heading.This vision sensor 1 is measured the distance of vehicle and lane mark in real time based on machine vision principle, and output parameter comprises that vehicle changes with the corresponding vehicle of left-hand lane linear distance dL(track to the left), vehicle changes with the corresponding vehicle of right-hand lane linear distance dR(track to the right).
Car speed sensor is arranged on the change-speed box of vehicle, and car speed sensor is magneto-electric car speed sensor, and the sampling precision of this car speed sensor is 0.01km/h.Car speed sensor can utilize the self-contained car speed sensor of vehicle, is conducive to reduce costs.For example, car speed sensor is magneto-electric car speed sensor, and its sampling precision is 0.01km/h.The mouth of car speed sensor is electrically connected to vehicle-mounted CAN bus 4, for the vehicle speed signal collecting is transferred to vehicle-mounted CAN bus 4.
With reference to Fig. 2, for a kind of process of changing of the present invention is got over the line circuit connection diagram of prediction unit constantly.Car speed sensor is electrically connected to vehicle-mounted CAN bus 4, and data processing unit 2 is electrically connected to respectively vehicle-mounted CAN bus 4 and vision sensor 1.In the embodiment of the present invention, for the ease of realizing data transmission, CAN can also be set and turn RS485 serial port protocol conv 3, RS485 intelligent CAN conv 3 is fixedly mounted on to idle place, operator's compartment operation bench below, for obtaining the vehicle speed data on vehicle CAN bus.Vehicle-mounted CAN bus 4 is electrically connected to the input end that CAN turns RS485 serial port protocol conv 3, and ARM9 treater is electrically connected to respectively by I/O interface in-phase end and the end of oppisite phase that CAN turns RS485 serial port protocol conv 3.ARM9 treater also can adopt following connection mode with vehicle-mounted CAN bus 4: the I/O interface of ARM9 treater is connected to vehicle-mounted CAN bus 4 by CAN controller, CAN transceiver successively.
When exchange road is got over line and constantly predicted, because the time that lane changing itself is lasting is shorter, therefore, the processing speed of the sampling frequency of vision sensor 1 and ARM9 treater must meet changes early warning and changes the requirement of getting over line moment prediction unit.The sampling frequency of the vision sensor 1 adopting in the embodiment of the present invention is 10Hz, and vision sensor can be exported No. 10 vehicles 1 each second apart from the distance of lane mark.The processing set of frequency of ARM9 treater is 10Hz, Ji Huan road more line constantly prediction unit can carry out the more line of 10 times each second and constantly predict, meet to change and get over the line requirement of prediction unit constantly, and the frequency of operation of lane mark sensor and treater is consistent, there will not be and processes the phenomenon lagging behind.
The vehicle of take changes left as example, according to above process, completes after device installation, just need to get over line prediction constantly according to the following steps process of changing:
First need to carry out raw data acquisition.Owing to changing the references object of getting over line, be lane mark, therefore based on vehicle and lane mark distance parameter, can accurately express vehicle lane-changing and get over the line moment.In the embodiment of the present invention, in employing vision sensor exchange road process, vehicle and lane mark distance are measured, and this vision sensor is measured the distance of vehicle and lane mark in real time based on machine vision principle, and output parameter comprises vehicle and left-lane linear distance.The real-time vehicle running speed of car speed sensor collection is sent in vehicle-mounted CAN bus 4.Like this, make vehicle in advance repeatedly to the left track change, changing in process at every turn, data processing unit acquisition time parameter, the transverse distance that vision sensor detects vehicle and left-lane line is sent to data processing unit; Meanwhile, car speed sensor is sent to data processing unit by the real-time speed of a motor vehicle by vehicle-mounted CAN bus.
Then set up vehicle lane-changing matching relational database, for vehicle, change in track to the left, first, the difference of the speed of a motor vehicle, divides into groups the original data of data processing unit collection when changing; Original data comprises: the vehicle obtaining in raw data acquisition and the transverse distance of left-lane line and corresponding acquisition time.In the embodiment of the present invention, after obtaining respectively organizing original data, every group of original data carried out to the matching of M order polynomial, thereby obtain vehicle and change matching relational database left, described vehicle changes matching relational database left and comprises that vehicle corresponding under different speed of a motor vehicle conditions changes vehicle corresponding under cross travel matched curve, different speed of a motor vehicle condition left and changes cross travel polynomial fitting left and respectively organize original data.The size of M and the really degree of matched curve are closely related, and in order to guarantee the accuracy of polynomial fitting, M gets the natural number that is greater than 3, and for example, in embodiments of the present invention, M gets 7.
According to said process, can obtain under the various typical speed of a motor vehicle conditions vehicle and change cross travel matched curve, vehicle left and change cross travel polynomial fitting left and respectively organize original data.The cross travel curve that we change cross travel matched curve and vehicle lane-changing process reality left to vehicle contrasts, can find, under various speed of a motor vehicle conditions, both fitting coefficients all reach more than 0.999, error of fitting is controlled in very little scope, the tendency of all matched curves has well characterized the variation tendency of the cross travel of vehicle lane-changing process reality, and this shows that vehicle based on 7 order polynomial matchings changes cross travel matched curve left and can correctly characterize the actual track that changes.Therefore, by a large amount of real train tests, utilize vision sensor to gather transverse distance and the time parameter between this car and lane mark in different speed of a motor vehicle condition Xia Huan road process, and to changing each time the parameter of process, carry out 7 order polynomial matchings respectively, draw respectively the curve of 7 polynomial fittings.It should be noted that in addition, similar for fitting result under identical speed of a motor vehicle condition or overlap matched curve, these matched curves are screened separately, therefrom select and can represent this group curve tendency Huan road track, repeat according to the method described above to select matched curve, until equal selected the completing of matched curve.
Then carry out measured data collection: its detailed process is as follows: when vehicle carries out that track is changed to the left, data processing unit acquisition time parameter, vision sensor detects the transverse distance of vehicle and left-lane line, and the transverse distance of vehicle and left-lane line is sent to data processing unit; Meanwhile, car speed sensor is sent to data processing unit by the real-time speed of a motor vehicle by vehicle-mounted CAN bus.
Then obtain more line required cross travel matching relational expression constantly of prediction: when to certain, once Huan road is predicted constantly, need to be according to the measured data of a period of time in Gai Cihuan road process, change and get over line and constantly predict.Detailed process is as follows: in the setting-up time section after vehicle starts to change, the measured data of data processing unit collection is carried out to 7 order polynomial matchings, draw 7 order polynomial f
1and f
1matched curve, the starting point Wei Huan road zero hour of setting-up time section.In embodiments of the present invention, in setting-up time section the measured data of data processing unit collection be prediction change get over line constantly according to one of.For installation, change the vehicle of forewarn system, from vehicle, start Huan Daodaohuan road forewarn system and identify vehicle lane-changing for need to expend the regular hour, from vehicle, start to occur cross travel Dao Huan road forewarn system and identify between the behavior of changing life period and postpone, setting certain, to change the zero hour be t
0the moment that ，Huan road forewarn system identifies lane changing behavior is t
1, setting-up time section can be made as from moment t
0to moment t
1time period.
Above-mentioned measured data is included in the vehicle that obtains in measured data collection and the transverse distance of left-lane line and the corresponding acquisition time with it; For example, when vehicle Huan road starts and the transverse distance of left-lane line be 0.6m, corresponding acquisition time is 0s with it; 0.2s after vehicle Huan road starts, the transverse distance of vehicle and left-lane line is 0.5m, corresponding acquisition time is 0.2s so with it.At vehicle, change left in matching relational database, according to the setting of setting-up time section, every group of original data is divided into and is positioned at the leading portion original data of corresponding setting-up time section and is positioned at corresponding setting-up time section back segment original data afterwards.For example setting-up time section is 0.8s, and front end original data Zhi Huan road starts the original data collecting in rear 0.8s, and back segment original data Zhi Huan road starts rear 0.8s Zhi Huan road and gets over the original data that line constantly gathers.Leading portion original data be change get over that line predicts constantly according to one of.
Respectively each group leading portion original data is carried out to 7 order polynomial matchings, obtain several 7 order polynomials and several corresponding matched curves; In these several matched curves, select and f
1the immediate matched curve L of matched curve
w, and with matched curve L
w7 corresponding order polynomial f
w; At vehicle, change left in matching relational database, obtain and above-mentioned 7 order polynomial f
wcorresponding leading portion original data D
wf, and with leading portion original data D
wfcorresponding back segment original data D
wb; By back segment original data D
wbmeasured data combination with data processing unit gathers in setting-up time section, forms predicted data.In predicted data, back segment original data D
wbbe historical data, to be vehicle carrying out this measured data while changing to the measured data that data processing unit gathers in setting-up time section.Then above-mentioned predicted data is carried out to 7 order polynomial matchings, obtain more line projected relationship formula y=f (t) constantly, y represents the transverse distance of vehicle and left-lane line, and t represents to change and gets over the line moment.
Determine to change and get over line constantly: from the more line of vehicle movement process Er Yan，Huan road process, be constantly subject to the impact of two factors: the one, the distance of vehicle and lane mark, for changing to conflict, constantly there is material impact with the distance of lane mark in vehicle.Change vehicle in process, with respect to lane mark, lasting cross travel occurs, from current time, after certain cross travel occurs vehicle, vehicle will be pressed onto lane mark.Next is cross travel and the relation between the time in vehicle Huan road process.For certain, change, if cross travel and the functional relation between the time in known vehicle Huan road process, as long as by vehicle with lane mark apart from this functional relation of substitution, can solve to change and get over the line moment.Therefore, track in vehicle Huan road process can be regarded as and take longitudinal direction of car and be laterally the curve of coordinate axle, when analyzing this track, researchist is taken as 0 by the longitudinal acceleration of vehicle conventionally, be that in vehicle Huan road process, longitudinally speed of a motor vehicle maintenance is stable, on the other hand, even if changing longitudinal speed of a motor vehicle in process changes a lot, in Dan Huan road process, vehicle body and lane mark angle are conventionally less, thereby make the variation of vehicular longitudinal velocity very little on cross velocity impact, therefore, can be set in while changing vehicular longitudinal velocity substantially constant, longitudinal travel y can be expressed as take the function that the time is independent variable, in Ze Huan road process, cross travel can be expressed as take the function that longitudinal travel is independent variable, thereby becoming, cross travel take the function that the time is independent variable.More line moment projected relationship formula y=f (t) has just represented the corresponding relation of cross travel and time.Therefore, in acquisition, get over line moment projected relationship formula y=f (t) afterwards, at this, change in process, after setting-up time section, data processing unit obtains the transverse distance of vehicle and left-lane line in real time, the transverse distance substitution of this vehicle and left-lane line is got in line moment projected relationship formula y=f (t), draw to change and get over line constantly.
In embodiments of the present invention, when vehicle carry out track to the right change Shi，Qi Huan road more the Forecasting Methodology of line time and vehicle carry out track to the left and change Dao Shihuan road more the Forecasting Methodology of line time is similar, at this, no longer repeat.
In sum, groundwork of the present invention is by gather this car and the transverse distance of left and right, track, this car place lane mark and corresponding time parameter with vision sensor, by a large amount of real train tests, obtain abundant distance and time parameter, and take the time and carry out 7 order polynomial matchings as independent variable exchange road process, set up vehicle lane-changing matching relational database, according to this vehicle lane-changing matching relational database, obtain more line moment projected relationship formula.When practical application, from chaufeur, starting Huan Daodaohuan road forewarn system identifies and between lane-changing intention of driver, has the regular hour postpone, system is by detecting the lane-changing intention of chaufeur, when recognizing chaufeur and start to change, delay time to this before constantly, this car in section carried out 7 order polynomial matchings with lane mark transverse distance and time parameter, matched curve comparison by fitting result with the vehicle lane-changing matching corresponding stage of relational database, find out immediate matched curve, thereby obtain more line moment projected relationship formula.
Obviously, those skilled in the art can carry out various changes and modification and not depart from the spirit and scope of the present invention the present invention.Like this, if within of the present invention these are revised and modification belongs to the scope of the claims in the present invention and equivalent technologies thereof, the present invention is also intended to comprise these changes and modification interior.
Claims (8)
1.Yi Zhonghuan road process is got over line prediction unit constantly, it is characterized in that, comprising: vehicle-mounted CAN bus (4), data processing unit (2), be arranged on the vision sensor (1) of vehicle front windshield top and be arranged on the car speed sensor on transmission for vehicles;
Described car speed sensor is electrically connected to vehicle-mounted CAN bus (4), and described data processing unit (2) is electrically connected to respectively vehicle-mounted CAN bus (4) and vision sensor (1).
2. a kind of process of changing as claimed in claim 1 is got over line prediction unit constantly, it is characterized in that, described vision sensor (1) is towards vehicle front road surface, and the survey precision of described vision sensor (1) is 5cm, measurement range is ± 635cm that output frequency is 10Hz.
3. a kind of process of changing as claimed in claim 1 is got over line prediction unit constantly, it is characterized in that, described data processing unit (2) is encapsulated in can; Described data processing unit (2) is electrically connected to respectively vehicle-mounted CAN bus (4) and vision sensor (1) by I/O interface, and the data sampling frequency of described data processing unit (2) is 10Hz.
4. a kind of process of changing as claimed in claim 1 is got over line prediction unit constantly, it is characterized in that, described car speed sensor is magneto-electric car speed sensor, and the sampling precision of described car speed sensor is 0.01km/h.
5. a kind of process of changing as claimed in claim 1 is got over line prediction unit constantly, it is characterized in that, the mouth of described data processing unit (2) is electrically connected with read-out, and described read-out is arranged on meter panel of motor vehicle.
6.Yi Zhonghuan road process is got over line Forecasting Methodology constantly, based on a kind of process of changing claimed in claim 1, gets over line prediction unit constantly, it is characterized in that, comprises the following steps:
Raw data acquisition: make vehicle in advance repeatedly left/right-hand lane change, changing in process at every turn, data processing unit acquisition time parameter, the transverse distance that vision sensor detects vehicle and left/right lane mark is sent to data processing unit; Meanwhile, car speed sensor is sent to data processing unit by the real-time speed of a motor vehicle by vehicle-mounted CAN bus;
Set up vehicle lane-changing matching relational database: for vehicle left/right-hand lane changes, first, the difference of the speed of a motor vehicle, divides into groups the original data of data processing unit collection when changing, and obtains vehicle and changes matching relational database to left/right; Original data comprises: the vehicle obtaining in raw data acquisition and the transverse distance of left/right lane mark and corresponding acquisition time;
Measured data gathers: when carry out left/right-hand lane of vehicle is changed, data processing unit acquisition time parameter, vision sensor detects the transverse distance of vehicle and left/right lane mark, and the transverse distance of vehicle and left/right lane mark is sent to data processing unit; Meanwhile, car speed sensor is sent to data processing unit by the real-time speed of a motor vehicle by vehicle-mounted CAN bus;
Obtain more line required cross travel matching relational expression constantly of prediction: in the setting-up time section after vehicle starts to change, the measured data of data processing unit collection is carried out to the matching of M order polynomial, draw M order polynomial f
1and f
1matched curve, M is greater than 3 natural number, the starting point Wei Huan road zero hour of described setting-up time section, described measured data is included in the vehicle that obtains in measured data collection and the transverse distance of left/right lane mark and the corresponding acquisition time with it; At vehicle, to left/right, change in matching relational database, every group of original data is divided into and is positioned at the leading portion original data of corresponding setting-up time section and is positioned at the back segment original data after corresponding setting-up time section, respectively each group leading portion original data is carried out to the matching of M order polynomial, obtain several M order polynomials and several corresponding matched curves; In described several matched curves, obtain and f
1the immediate matched curve L of matched curve
w, and with matched curve L
wcorresponding M order polynomial f
w; At vehicle, to left/right, change in matching relational database, obtain and described M order polynomial f
wcorresponding leading portion original data D
wf, and with leading portion original data D
wfcorresponding back segment original data D
wb; By back segment original data D
wbthe measured data gathering in setting-up time section with data processing unit combines, form predicted data, then described predicted data is carried out to the matching of M order polynomial, obtain more line moment projected relationship formula y=f (t), y represents the transverse distance of vehicle and left/right lane mark, and t represents to change and gets over line constantly;
Determine to change and get over line constantly: the arbitrary moment after setting-up time section, the transverse distance of the vehicle that data processing unit is obtained and left/right lane mark, substitution is got in line moment projected relationship formula y=f (t), draws to change to get over line constantly.
7. a kind of process of changing as claimed in claim 6 is got over line Forecasting Methodology constantly, it is characterized in that, in setting up the process of vehicle lane-changing matching relational database, after obtaining respectively organizing original data, every group of original data carried out to the matching of M order polynomial, thereby obtain vehicle and change matching relational database to left/right, described vehicle changes matching relational database to left/right and comprises that vehicle corresponding under different speed of a motor vehicle conditions changes cross travel matched curve to left/right, under different speed of a motor vehicle conditions, corresponding vehicle changes cross travel polynomial fitting to left/right, and respectively organize original data.
8. a kind of process of changing as claimed in claim 6 is got over line Forecasting Methodology constantly, it is characterized in that, read-out is electrically connected to the mouth of data processing unit, after carrying out data processing, the more line in vehicle Huan road process is sent to read-out constantly.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310475750.XA CN103587528A (en) | 2013-10-12 | 2013-10-12 | Lane change process crossing moment prediction device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310475750.XA CN103587528A (en) | 2013-10-12 | 2013-10-12 | Lane change process crossing moment prediction device and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103587528A true CN103587528A (en) | 2014-02-19 |
Family
ID=50077923
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310475750.XA Pending CN103587528A (en) | 2013-10-12 | 2013-10-12 | Lane change process crossing moment prediction device and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103587528A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105740782A (en) * | 2016-01-25 | 2016-07-06 | 北京航空航天大学 | Monocular vision based driver lane-changing process quantization method |
| CN106004867A (en) * | 2016-05-31 | 2016-10-12 | 潍柴动力股份有限公司 | Lane changing overtaking control method and controller used for hybrid bus |
| CN106515577A (en) * | 2016-11-25 | 2017-03-22 | 长安大学 | Device for decreasing lane changing early warning false alarm rate and method of device |
| CN106956679A (en) * | 2016-01-11 | 2017-07-18 | 福特全球技术公司 | Autonomous vehicle Lane regulation |
| CN111090095A (en) * | 2019-12-24 | 2020-05-01 | 联创汽车电子有限公司 | Information fusion environment perception system and perception method thereof |
| CN114506324A (en) * | 2020-10-23 | 2022-05-17 | 上海汽车集团股份有限公司 | Lane decision method and related device |
| CN116110216A (en) * | 2022-10-21 | 2023-05-12 | 中国第一汽车股份有限公司 | Vehicle line crossing time determining method and device, storage medium and electronic device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070069874A1 (en) * | 2005-09-26 | 2007-03-29 | Gm Global Technology Operations, Inc. | Selectable lane-departure warning system and method |
| CN101894271A (en) * | 2010-07-28 | 2010-11-24 | 重庆大学 | Visual computing and prewarning method of deviation angle and distance of automobile from lane line |
| CN102336163A (en) * | 2011-08-31 | 2012-02-01 | 同济大学 | Vehicle yaw detection device |
| CN102785661A (en) * | 2012-08-20 | 2012-11-21 | 深圳先进技术研究院 | Lane departure control system and lane departure control method |
| CN203543950U (en) * | 2013-10-12 | 2014-04-16 | 长安大学 | Device for predicting line-crossing moment during lane-change process |
-
2013
- 2013-10-12 CN CN201310475750.XA patent/CN103587528A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070069874A1 (en) * | 2005-09-26 | 2007-03-29 | Gm Global Technology Operations, Inc. | Selectable lane-departure warning system and method |
| CN101894271A (en) * | 2010-07-28 | 2010-11-24 | 重庆大学 | Visual computing and prewarning method of deviation angle and distance of automobile from lane line |
| CN102336163A (en) * | 2011-08-31 | 2012-02-01 | 同济大学 | Vehicle yaw detection device |
| CN102785661A (en) * | 2012-08-20 | 2012-11-21 | 深圳先进技术研究院 | Lane departure control system and lane departure control method |
| CN203543950U (en) * | 2013-10-12 | 2014-04-16 | 长安大学 | Device for predicting line-crossing moment during lane-change process |
Non-Patent Citations (1)
| Title |
|---|
| 王畅: "车辆换道预警的若干关键问题研究", 《中国博士学位论文全文数据库工程科技Ⅱ辑》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106956679B (en) * | 2016-01-11 | 2022-05-31 | 福特全球技术公司 | Autonomous vehicle lane management |
| CN106956679A (en) * | 2016-01-11 | 2017-07-18 | 福特全球技术公司 | Autonomous vehicle Lane regulation |
| CN105740782A (en) * | 2016-01-25 | 2016-07-06 | 北京航空航天大学 | Monocular vision based driver lane-changing process quantization method |
| CN105740782B (en) * | 2016-01-25 | 2019-02-22 | 北京航空航天大学 | A kind of driver's lane-change course quantization method based on monocular vision |
| CN106004867A (en) * | 2016-05-31 | 2016-10-12 | 潍柴动力股份有限公司 | Lane changing overtaking control method and controller used for hybrid bus |
| CN106515577B (en) * | 2016-11-25 | 2020-05-05 | 长安大学 | Device and method for reducing false alarm rate of channel change early warning |
| CN106515577A (en) * | 2016-11-25 | 2017-03-22 | 长安大学 | Device for decreasing lane changing early warning false alarm rate and method of device |
| CN111090095A (en) * | 2019-12-24 | 2020-05-01 | 联创汽车电子有限公司 | Information fusion environment perception system and perception method thereof |
| CN111090095B (en) * | 2019-12-24 | 2023-03-14 | 上海汽车工业(集团)总公司 | Information fusion environment perception system and perception method thereof |
| CN114506324A (en) * | 2020-10-23 | 2022-05-17 | 上海汽车集团股份有限公司 | Lane decision method and related device |
| CN114506324B (en) * | 2020-10-23 | 2024-03-15 | 上海汽车集团股份有限公司 | Lane decision method and related device |
| CN116110216A (en) * | 2022-10-21 | 2023-05-12 | 中国第一汽车股份有限公司 | Vehicle line crossing time determining method and device, storage medium and electronic device |
| CN116110216B (en) * | 2022-10-21 | 2024-04-12 | 中国第一汽车股份有限公司 | Vehicle line crossing time determining method and device, storage medium and electronic device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103587528A (en) | Lane change process crossing moment prediction device and method | |
| CN107672589B (en) | A kind of track of vehicle real-time predicting method and device based on GPR Detection Data | |
| CN102167041B (en) | Method for determining driving state of vehicle based on acceleration sensor | |
| CN101837781B (en) | Model based predictive control for automated lane centering/changing control systems | |
| CN103256939B (en) | Intelligent vehicle utilizes and becomes the method that granularity right of way radar map carries out information fusion | |
| CN102951152B (en) | For analyzing method and the device of vehicle to the close close situation of recoil simulator | |
| CN103909930A (en) | Method for auxiliary control of traveling along with vehicle ahead | |
| CN108737955A (en) | LDW/LKA test evaluation system and methods based on virtual lane line | |
| CN104386063A (en) | Driving assistance system based on artificial intelligence | |
| CN105761546B (en) | A kind of methods, devices and systems of vehicle collision avoidance | |
| CN102991505B (en) | A kind of road ahead Curvature Estimation method | |
| CN203739885U (en) | Track control system for line marking vehicle | |
| CN103625472A (en) | Smart cruise control apparatus and method thereof | |
| CN104871204A (en) | Vehicle-mounted image processing device | |
| CN103884293A (en) | Tire deformation online testing device and testing method based on light streams | |
| CN112748421A (en) | Laser radar calibration method based on automatic driving of straight road section | |
| CN105242569A (en) | Hardware-in-the-loop simulation test bench for automobile AFS | |
| CN104627068A (en) | Computing system and method for car body course angle in automatic parking process | |
| CN105216626A (en) | The intelligent instruments in vehicles of battery-driven car | |
| CN203739886U (en) | Active lane keeping device based on EPS | |
| CN109443374A (en) | Lane line emerging system and its fusion method | |
| CN103587529B (en) | A kind of straight way section lane-change process gets over line moment forecasting system and Forecasting Methodology | |
| CN203543950U (en) | Device for predicting line-crossing moment during lane-change process | |
| CN203332108U (en) | Dangerous driving behavior recognition device | |
| CN104608768A (en) | Distinguishing device and method of curve entering and lane changing of front target vehicle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140219 |